{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SX2VDE4LB4SD4MBBTLSM5PGB6I","short_pith_number":"pith:SX2VDE4L","schema_version":"1.0","canonical_sha256":"95f551938b0f243e30219ae4cebcc1f22e8f454d4f933cd23bee78937eb78180","source":{"kind":"arxiv","id":"2310.18343","version":2},"attestation_state":"computed","paper":{"title":"PHD: Pixel-Based Language Modeling of Historical Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Desmond Elliott, Isabelle Augenstein, Nadav Borenstein, Phillip Rust","submitted_at":"2023-10-22T08:45:48Z","abstract_excerpt":"The digitisation of historical documents has provided historians with unprecedented research opportunities. Yet, the conventional approach to analysing historical documents involves converting them from images to text using OCR, a process that overlooks the potential benefits of treating them as images and introduces high levels of noise. To bridge this gap, we take advantage of recent advancements in pixel-based language models trained to reconstruct masked patches of pixels instead of predicting token distributions. Due to the scarcity of real historical scans, we propose a novel method for "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.18343","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-22T08:45:48Z","cross_cats_sorted":[],"title_canon_sha256":"87ad7d438dc0e3b28915f029ec7768d93210c4b35cd5e9a3fe6ddc72993792da","abstract_canon_sha256":"4f4ebcf561d19b89de502b7c2966939f5d347c74f2f9b027237655872a56d3e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:03.832326Z","signature_b64":"i+LbjGHYkOhe+Dog1F4JT/sjYcZ/yaljPviC/PadTN4Bmh1T/dKkGN2brXq61/O7kV7ChmeSTFmVH5BQJ0WzDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95f551938b0f243e30219ae4cebcc1f22e8f454d4f933cd23bee78937eb78180","last_reissued_at":"2026-07-05T07:09:03.831864Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:03.831864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PHD: Pixel-Based Language Modeling of Historical Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Desmond Elliott, Isabelle Augenstein, Nadav Borenstein, Phillip Rust","submitted_at":"2023-10-22T08:45:48Z","abstract_excerpt":"The digitisation of historical documents has provided historians with unprecedented research opportunities. Yet, the conventional approach to analysing historical documents involves converting them from images to text using OCR, a process that overlooks the potential benefits of treating them as images and introduces high levels of noise. To bridge this gap, we take advantage of recent advancements in pixel-based language models trained to reconstruct masked patches of pixels instead of predicting token distributions. Due to the scarcity of real historical scans, we propose a novel method for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18343","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.18343/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.18343","created_at":"2026-07-05T07:09:03.831937+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.18343v2","created_at":"2026-07-05T07:09:03.831937+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18343","created_at":"2026-07-05T07:09:03.831937+00:00"},{"alias_kind":"pith_short_12","alias_value":"SX2VDE4LB4SD","created_at":"2026-07-05T07:09:03.831937+00:00"},{"alias_kind":"pith_short_16","alias_value":"SX2VDE4LB4SD4MBB","created_at":"2026-07-05T07:09:03.831937+00:00"},{"alias_kind":"pith_short_8","alias_value":"SX2VDE4L","created_at":"2026-07-05T07:09:03.831937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SX2VDE4LB4SD4MBBTLSM5PGB6I","json":"https://pith.science/pith/SX2VDE4LB4SD4MBBTLSM5PGB6I.json","graph_json":"https://pith.science/api/pith-number/SX2VDE4LB4SD4MBBTLSM5PGB6I/graph.json","events_json":"https://pith.science/api/pith-number/SX2VDE4LB4SD4MBBTLSM5PGB6I/events.json","paper":"https://pith.science/paper/SX2VDE4L"},"agent_actions":{"view_html":"https://pith.science/pith/SX2VDE4LB4SD4MBBTLSM5PGB6I","download_json":"https://pith.science/pith/SX2VDE4LB4SD4MBBTLSM5PGB6I.json","view_paper":"https://pith.science/paper/SX2VDE4L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.18343&json=true","fetch_graph":"https://pith.science/api/pith-number/SX2VDE4LB4SD4MBBTLSM5PGB6I/graph.json","fetch_events":"https://pith.science/api/pith-number/SX2VDE4LB4SD4MBBTLSM5PGB6I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SX2VDE4LB4SD4MBBTLSM5PGB6I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SX2VDE4LB4SD4MBBTLSM5PGB6I/action/storage_attestation","attest_author":"https://pith.science/pith/SX2VDE4LB4SD4MBBTLSM5PGB6I/action/author_attestation","sign_citation":"https://pith.science/pith/SX2VDE4LB4SD4MBBTLSM5PGB6I/action/citation_signature","submit_replication":"https://pith.science/pith/SX2VDE4LB4SD4MBBTLSM5PGB6I/action/replication_record"}},"created_at":"2026-07-05T07:09:03.831937+00:00","updated_at":"2026-07-05T07:09:03.831937+00:00"}